© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50587
    Prev
    Next
    INDEX
    Explanations

    have or take

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :both
    -0.07
    æĥħçIJĨ
    -0.07
    å¾Ĺå¿ĥ
    -0.07
    è±ģ
    -0.07
    è¿ĩå¿«
    -0.06
    è¿Ľè¡ĮæŶ
    -0.06
     kej
    -0.06
    ãģĦãģĭ
    -0.06
    æĢİ
    -0.06
     RequestMethod
    -0.06
    POSITIVE LOGITS
    ãģĤãĤĭ
    0.09
    ä¸Ģ群人
    0.09
    ä¸Ģ群
    0.08
    åĪ°çļĦ
    0.08
    è¿Ļæł·ä¸Ģ个
    0.08
    âm
    0.07
    leb
    0.07
    ãm
    0.07
    ä½łçľŁ
    0.07
    ä¸Ģ个æĸ°
    0.07
    Activations Density 0.183%

    No Known Activations